© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119089
    Prev
    Next
    INDEX
    Explanations

    specifics and differentiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     عندما
    -0.06
    その他
    -0.06
     takip
    -0.06
     সুস্থ
    -0.06
     лучшие
    -0.06
     சம்பந்த
    -0.05
     ஆண்க
    -0.05
    icultura
    -0.05
     dimana
    -0.05
     राहि
    -0.05
    POSITIVE LOGITS
     specific
    0.07
     specifics
    0.07
     به‌
    0.07
    specific
    0.07
     தொழில
    0.07
     differentiation
    0.06
     drib
    0.06
     específico
    0.06
    agawa
    0.06
     contradictory
    0.06
    Activations Density 0.001%

    No Known Activations